Summary
Juan Banda is a Lead Data Scientist with nine years of hands-on experience turning messy, multi-modal datasets into production-ready machine learning and retrieval systems, currently driving responsible AI adoption at Stanford Health Care. He has deep expertise in large-scale image feature extraction for content-based image retrieval (including work for the NASA SDO mission) and in clinical NLP and phenotyping across millions of EHR records, authoring tools like the APHRODITE phenotyping package and OHDSI2RDF. Equally comfortable as a researcher and engineer, he builds ETL pipelines, production APIs, and web front-ends while routinely coding in Python, R, SQL, Matlab and maintaining legacy systems. His background spans academia and industry—from leading a lab at Georgia State University to long-term collaborations with OHDSI—giving him a rare combination of reproducible research practice and production software delivery. Collected across diverse languages and platforms, his toolkit and track record make him particularly effective at migrating legacy codebases and productizing research prototypes for clinical applications.
9 years of coding experience
23 years of employment as a software developer
Ph.D Computer Science, Ph.D Computer Science at Montana State University-Bozeman
Postgraduate Degree Medical Informatics, Postgraduate Degree Medical Informatics at Stanford University School of Medicine
Masters Mathematics, Masters Mathematics at Eastern New Mexico University
Bachelors Computer Science, Bachelors Computer Science at Universidad Autonoma de Chihuahua
Spanish, English